{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:06:45Z","timestamp":1783530405074,"version":"3.55.0"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3164261","type":"journal-article","created":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T19:52:14Z","timestamp":1648842734000},"page":"3694-3708","source":"Crossref","is-referenced-by-count":15,"title":["MAVEN: A Memory Augmented Recurrent Approach for Multimodal Fusion"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4207-5863","authenticated-orcid":false,"given":"Md Mofijul","family":"Islam","sequence":"first","affiliation":[{"name":"School of Engineering and Applied Science, University of Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4684-2823","authenticated-orcid":false,"given":"Mohammad Samin","family":"Yasar","sequence":"additional","affiliation":[{"name":"School of Engineering and Applied Science, University of Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0133-1234","authenticated-orcid":false,"given":"Tariq","family":"Iqbal","sequence":"additional","affiliation":[{"name":"School of Engineering and Applied Science, University of Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1152\/jn.1986.56.3.640"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.17-07-02429.1997"},{"key":"ref3","first-page":"689","article-title":"Multimodal Deep Learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ngiam","year":"2011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/9781119170174.epcn214"},{"key":"ref5","first-page":"13","article-title":"Multisensory perception","volume-title":"Multisensory Perception","author":"Sathian","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340987"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00875"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793954"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3059624"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19988"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01330"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2808769"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.456"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1211"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref19","first-page":"5265","article-title":"VisualBERT: A simple and performant baseline for vision and language","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2019"},{"key":"ref20","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916887"},{"key":"ref22","article-title":"Audiovisual slowfast networks for video recognition","author":"Xiao","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3123021.3123046"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2738401"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/1073858406287908"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2005.06.008"},{"key":"ref28","first-page":"12805","article-title":"Brain-like object recognition with high-performing shallow recurrent ANNs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kubilius","year":"2019"},{"key":"ref29","first-page":"9201","article-title":"Deep predictive coding network with local recurrent processing for object recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han","year":"2018"},{"key":"ref30","first-page":"5173","article-title":"Saliency-based sequential image attention with multiset prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Welleck","year":"2017"},{"key":"ref31","first-page":"3225","article-title":"Attend, infer, repeat: Fast scene understanding with generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Eslami","year":"2016"},{"key":"ref32","article-title":"Recurrent independent mechanisms","author":"Goyal","year":"2019"},{"key":"ref33","first-page":"11525","article-title":"Object-centric learning with slot attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Locatello","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1719397115"},{"key":"ref35","article-title":"Brain-inspired recurrent neural algorithms for advanced object recognition","author":"Schrimpf","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-019-0392-5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-2236(00)01657-X"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/nrn3476"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.42870"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1523\/jneurosci.3825-12.2013"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/BF02259139"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7350781"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683898"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12319"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093616"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00630"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.486"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018561"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968615"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_7"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967570"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref61","article-title":"Variational attention for sequence-to-sequence models","author":"Bahuleyan","year":"2017"},{"key":"ref62","first-page":"9712","article-title":"Latent alignment and variational attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Deng","year":"2018"},{"key":"ref63","article-title":"Auto-encoding variational bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Representations","author":"Kingma","year":"2013"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/109"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref66","article-title":"Pytorch lightning","author":"Falcon","year":"2019"},{"key":"ref67","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2016"},{"key":"ref68","article-title":"Distilling the knowledge in a neural network","volume-title":"NIPS Deep Learn. Representation Learn. Workshop","author":"Hinton","year":"2015"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2013.6474999"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2628339"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2678539"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.4018\/IJMDEM.2015100102"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.123"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCI.2016.7732038"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2018.2884443"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00127"},{"key":"ref78","first-page":"5999","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1266"},{"key":"ref80","article-title":"Adversarial autoencoders","volume-title":"Int. Conf. Learn. Representations","author":"Makhzani","year":"2016"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09747989.pdf?arnumber=9747989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T00:22:57Z","timestamp":1705537377000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747989\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3164261","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}